© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198143
    Prev
    Next
    INDEX
    Explanations

    with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    1.02
    ri
    0.92
    db
    0.91
    ug
    0.86
     I
    0.84
    I
    0.83
    den
    0.83
    di
    0.82
    del
    0.82
    ].
    0.80
    POSITIVE LOGITS
    ча
    1.11
    ו
    1.10
    ту
    1.09
    3
    1.04
    ме
    1.00
    то
    0.99
    2
    0.97
    وني
    0.96
    の
    0.96
    ции
    0.96
    Activations Density 0.057%

    No Known Activations